Bayesian and frequentist inference are two fundamental paradigms in statistical estimation.
Bayesian methods treat hypotheses as random variables, incorporating priors and updating …

Low-Rank Adaptation (LoRA) enables parameter-efficient fine-tuning of large language
models by decomposing weight updates into low-rank matrices, significantly reducing …

Test time adaptation (TTA) equips deep learning models to handle unseen test data that
deviates from the training distribution, even when source data is inaccessible. While …

Deep neural networks are misguided by simple-to-craft, imperceptible adversarial
perturbations to inputs. Now, it is possible to craft such perturbations solely using model …